zai-org / KaleidoLinks
Kaleido: Open-sourced multi-subject reference video generation model, enabling controllable, high-fidelity video synthesis from multiple image references.
☆87Updated last week
Alternatives and similar repositories for Kaleido
Users that are interested in Kaleido are comparing it to the libraries listed below
Sorting:
- [Arxiv'25] IC-Custom: Diverse Image Customization via In-Context Learning☆158Updated 3 months ago
- FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation☆77Updated 4 months ago
- MoviiGen 1.1: Towards Cinematic-Quality Video Generative Models☆181Updated 5 months ago
- [AAAI 2026] Minute-Long Videos with Dual Parallelisms☆43Updated last month
- Concat-ID: Towards Universal Identity-Preserving Video Synthesis☆65Updated 7 months ago
- ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback☆121Updated 3 months ago
- [ICCV 2025] Code & Data for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing☆164Updated 5 months ago
- Code for full fintuing Mochi model with FSDP (and CP)☆31Updated 5 months ago
- Blending Custom Photos with Video Diffusion Transformers☆48Updated 11 months ago
- [AAAI 2026] We present LAMIC, a Layout-Aware Multi-Image Composition framework, that extends single-reference diffusion models to multi-r…☆26Updated 4 months ago
- ☆79Updated 9 months ago
- Unofficial extension implementation of CausVid☆70Updated 7 months ago
- Generate image at any resolution.☆41Updated 3 months ago
- ☆51Updated last week
- [ICLR 2025] Official lmplementation of SPM-Diff: Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On☆45Updated 9 months ago
- [NeurIPS 2025 Spotlight] LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation☆83Updated last week
- UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios☆85Updated last week
- Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback☆192Updated last week
- ☆32Updated 9 months ago
- Code of RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images☆94Updated last year
- Official implementation of CVPR 2025 paper "ID-Patch: Robust ID Association for Group Photo Personalization". This work proposed propose …☆73Updated 7 months ago
- [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".☆116Updated 7 months ago
- StreamDiffusion, Live Stream APP☆283Updated 2 weeks ago
- 🔥🔥 Official Repo of UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward☆174Updated 3 months ago
- Official PyTorch implementation of the paper "FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing"☆72Updated last week
- HyperMotion is a pose guided human image animation framework based on a large-scale video diffusion Transformer.☆128Updated 5 months ago
- We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while a…☆83Updated this week
- MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance☆26Updated last year
- An official implementation of SwapAnyone.☆72Updated 9 months ago
- [ICCV2025] DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation☆199Updated 6 months ago